Atlas / MCP servers / amanhij / Zikkaron

ZikkaronSAFE

mcp/amanhij/zikkaron

Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
—
Transport
stdio · streamable-http
License
MIT
Stars
63
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://pypi.org/project/zikkaron/) [](https://www.python.org/downloads/) [](#testing) [](LICENSE)

Zikkaron (זיכרון) is Hebrew for "memory."

Your AI forgets you every time you close the tab. Every architecture decision you explained, every debugging rabbit hole you went down together, every "remember, we're using Postgres not SQLite" correction. Gone. You start the next session a stranger to your own tools.

Zikkaron is a persistent memory engine for Claude Code built on computational neuroscience. It remembers what you worked on, how you think, what you decided and why. Not as a dumb text dump that gets shoved into context, but as a living memory system that consolidates, forgets intelligently, and reconstructs the right context at the right time.

26 subsystems. 24 MCP tools. Runs entirely on your machine. One SQLite file.

Two minutes to never repeat yourself again

pip install zikkaron

Add to your Claude Code config:

{
"mcpServers": {
"zikkaron": {
"command": "zikkaron"
}
}
}

Tell Claude how to use it. Drop this in your global ~/.claude/CLAUDE.md (your home directory, not per-project):

## Memory
- On every new session, call `recall` with the current project name
- Before starting any task, call `get_project_context` for the current directory
- After completing significant work, call `remember` to store decisions and outcomes

Or just let Zikkaron handle it. On every startup, it automatically syncs ~/.claude/CLAUDE.md with the latest instructions via sync_instructions. You set it up once and never think about it again.

What this actually feels like

Monday. You spend an hour debug

Read from source at commit cf78d0c2200dOBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (pypi)
claude mcp add zikkaron -- None zikkaron==1.4.0
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (3 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (5)

LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:360
"url": "http://127.0.0.1:8742/sse"
LOWObfuscation / stealth · obf.homoglyph · CWE-506, CWE-94
benchmarks/run_locomo_ablation.py:476
"Δoverall | Δopen | Max drop | Overall 95% CI | Open 95% CI | Win/Loss/Tie (overall) | Target |\n"
LOWObfuscation / stealth · obf.homoglyph · CWE-506, CWE-94
benchmarks/run_locomo_ablation.py:518
"| Run | overall MRR | open_domain MRR | Δoverall vs combined | Δopen vs combined |\n"
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements.txt
fastapi, sse-starlette, uvicorn, mcp, sentence-transformers, watchdog, pydantic, pydantic-settings
Why it matters. 11 requirement(s) not pinned with ==
Fix. pin exact versions
LOWInventory / provenance · mcp.no_tools_extracted · CWE-1104
server.json
Why it matters. the tool list is enumerated at runtime by tools/list, not declared in source
Fix. the page says so rather than showing an empty table

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha cf78d0c2200dfull audit observations/trust-audit/mcp-server/amanhij__zikkaron.json · Report an issue / request a re-scan
04

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07cf78d0c2200dSAFEB89first audit
05

Questions

What is the Zikkaron MCP server?

Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.

Is Zikkaron safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Zikkaron need?

It reads GEMINI_API_KEY and GOOGLE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Zikkaron run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as zikkaron.

How current is this page?

The grade is for one exact copy of the source (cf78d0c2200d), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement